© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12242
    Prev
    Next
    INDEX
    Explanations

    references to audio equipment and sound-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and concepts related to audio technology, recording, and sound production.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bilder
    -0.35
    碌
    -0.32
    ########.
    -0.31
     cameras
    -0.31
    目が
    -0.30
     Vein
    -0.30
    的看着
    -0.30
    █
    -0.30
     seeing
    -0.30
     painting
    -0.29
    POSITIVE LOGITS
     audio
    1.23
     Audio
    1.08
    audio
    1.07
    Audio
    1.07
     AUDIO
    1.00
     listeners
    0.95
     listener
    0.95
     áudio
    0.94
    AUDIO
    0.92
     headphones
    0.90
    Activations Density 0.272%

    No Known Activations